TY - GEN
T1 - Automatic Data Augmentation Via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation
AU - Qin, Tiexin
AU - Wang, Ziyuan
AU - He, Kelei
AU - Shi, Yinghuan
AU - Gao, Yang
AU - Shen, DInggang
N1 - Funding Information:
The work was supported by the National Key Research and Development Program of China (2019YFC0118300), NSFC (61432008, 61673203, 81927808), and Jiangsu Provincial Key Research and Development Project (BE2018610).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - Conventional data augmentation realized by performing simple pre-processing operations (e.g., rotation, crop, etc.) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovatively combine the data augmentation module and the subsequent segmentation module in an end-to-end training manner with a consistent loss. Specifically, the best sequential combination of different basic operations is automatically learned by directly maximizing the performance improvement (i.e., Dice ratio) on the available validation set. We extensively evaluated our method on CT kidney tumor segmentation which validated the promising results of our method.
AB - Conventional data augmentation realized by performing simple pre-processing operations (e.g., rotation, crop, etc.) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovatively combine the data augmentation module and the subsequent segmentation module in an end-to-end training manner with a consistent loss. Specifically, the best sequential combination of different basic operations is automatically learned by directly maximizing the performance improvement (i.e., Dice ratio) on the available validation set. We extensively evaluated our method on CT kidney tumor segmentation which validated the promising results of our method.
KW - Data augmentation
KW - Deep reinforcement learning
KW - Medical image segmentation
UR - http://www.scopus.com/inward/record.url?scp=85089216032&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053403
DO - 10.1109/ICASSP40776.2020.9053403
M3 - Conference contribution
AN - SCOPUS:85089216032
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1419
EP - 1423
BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Y2 - 4 May 2020 through 8 May 2020
ER -